Leaked chart suggests big perplexity jump in OpenAI's internal models
A KOL shared a leaked OpenAI-style log-perplexity chart claiming internal models made a major capability leap, closing a generational gap in two months, with Google training a comparable model; the claims remain unverified.
2026-11-23 ~ 2026-11-23 · 3 related posts
- Leaked OpenAI base-model perplexity chart shows roadmap up to GPT-6.2 Astra and an internal model cracking a Millennium Prize problem — iruletheworldmo · 2026-11-23
- OpenAI Leak: New Internal Model Shows Bigger Capability Jump Than GPT-5 to GPT-5.5 — ZeroStateReflex · 2026-11-23
- Leaked OpenAI loss curve suggests GPT-6.2 Astra solved a Millennium Prize problem, internal model already lower — kimmonismus · 2026-11-23